%matplotlib inline

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib import cm

import ipyparallel as ipp

from time import time
from datetime import datetime

import motif as mf

from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from sklearn.decomposition import PCA
from sklearn.utils import shuffle
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import roc_curve, roc_auc_score
from sklearn.model_selection import train_test_split, cross_val_score, cross_validate

from scipy.stats import spearmanr
from scipy.stats import pearsonr

Intel(R) Extension for Scikit-learn* enabled (https://github.com/intel/scikit-learn-intelex)

### set parameters for the motif analysis

PROTEIN_NAME = 'Klf9'
PROT_CONC = 0.1  # free protein concentration at binding reation; PBM typically 0.1 and RNACompete typically 0.002
BOTH_STRANDS = True  # wheter both strands are present for binding; True if double-stranded DNA or RNA is used as probes
#TIME_DISS = 1800  # experimental time span after binding reaction during which dissociation of the protein from the probe was possible

STAGES=mf.stage(protein=PROTEIN_NAME)

### read data

## RNAcompete sample data
#dfprobes_raw=pd.read_excel('./data/RNAcompete/A2BP1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/HNRNPA1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/PTBP1.xlsx')
#dfprobes_raw=pd.read_excel('./data/RNAcompete/RBM24.xlsx')


#dfprobes_raw=pd.read_csv('./data/samplePBMs/Mlx__pTH2882_HK.raw', sep='\t')
dfprobes_raw=pd.read_csv('./data/samplePBMs/Klf9__pTH2353_HK.raw', sep='\t')
#dfprobes_raw=pd.read_csv('./data/samplePBMs/Prdm11__pTH3455_HK.raw', sep='\t')
#dfprobes_raw=pd.read_csv('./data/samplePBMs/Sox10__pTH1729_HK.raw', sep='\t')


print('Columns of imported Data File: %s' % dfprobes_raw.columns)
#dfprobes_raw.describe()
#dfprobes_raw.info()

Columns of imported Data File: Index(['#id_spot', 'row', 'col', 'control', 'id_probe', 'pbm_sequence',
       'linker_sequence', 'mean_signal_intensity', 'mean_background_intensity',
       'flag'],
      dtype='object')

### select columns for probe sequence and signal

column_sequence = 'pbm_sequence'
column_signal = 'mean_signal_intensity'
background_signal = 'mean_background_intensity'  #set to None if not needed
#background_signal=None

#basic preprocessing
dfprobes_raw[column_signal] = dfprobes_raw[column_signal].apply(
    lambda a: np.NaN if a == ' ' else a)
dfprobes_raw[column_signal] = dfprobes_raw[column_signal].apply(
    lambda a: np.NaN if a == '' else a)
dfprobes_raw[column_sequence] = dfprobes_raw[column_sequence].apply(
    lambda a: np.NaN if str(a).lower() == 'nan' else a)
dfprobes_raw[column_sequence] = dfprobes_raw[column_sequence].apply(
    lambda a: np.NaN if a == '' else a)
dfprobes_raw = dfprobes_raw.dropna()

#construct new dataframe with only necessary data
if type(background_signal) == type(None):
    dfprobes = pd.DataFrame({
        'seq':
        dfprobes_raw[column_sequence].astype(str),
        'signal binding':
        dfprobes_raw[column_signal].astype(np.float32)
    })  #rebuild dataframe
else:
    dfprobes = pd.DataFrame({
        'seq':
        dfprobes_raw[column_sequence].astype(str),
        'signal':
        dfprobes_raw[column_signal].astype(np.float32),
        'background':
        dfprobes_raw[background_signal].astype(np.float32)
    })  #rebuild dataframe
    dfprobes['signal binding'] = dfprobes['signal'] - dfprobes['background']

dfprobes = dfprobes.dropna()    

    
# display main properties of data set
dfprobes['signal binding'].plot(figsize=(15, 5))
dfprobes.describe()

### check type of nucleic acid

dfprobes['seq'] = dfprobes['seq'].apply(
    lambda seq: seq.upper().replace(" ", ""))  #upper and remove blanks
dfprobes['RNA'] = dfprobes['seq'].apply(
    lambda seq: all(char in 'ACGU' for char in seq))
dfprobes['DNA'] = dfprobes['seq'].apply(
    lambda seq: all(char in 'ACGT' for char in seq))
non_RNA_counts = len(dfprobes[dfprobes['RNA'] == False])
non_DNA_counts = len(dfprobes[dfprobes['DNA'] == False])

if non_RNA_counts < non_DNA_counts:
    NUC_TYPE = 'RNA'
    print('I: RNA probes detected!')
else:
    NUC_TYPE = 'DNA'
    print('I: DNA probes detected!')

if NUC_TYPE == 'RNA' and non_RNA_counts != 0:
    print(
        'E: The probe sequences appear to be RNA, however there are some non-RNA nucleotides in the sequences.'
    )
    print('E: Please check the following sequnces %s' %
          dfprobes[dfprobes['RNA'] == False])

if NUC_TYPE == 'DNA' and non_DNA_counts != 0:
    print(
        'E: The probe sequences appear to be RNA, however there are some non-RNA nucleotides in the sequences.'
    )
    print('E: Please check the following sequnces %s' %
          dfprobes[dfprobes['DNA'] == False])

I: DNA probes detected!

### option to add a constant sequence at the 3' end and 5' end
sequence_to_be_added_5 = ''
sequence_to_be_added_3 = 'CCTGT'  # standard PBM arrays: CCTGTGTGAAATTGTTATCCGCTCT T7 array: GTCTTGA..
dfprobes['seq'] = sequence_to_be_added_5.upper(
) + dfprobes['seq'] + sequence_to_be_added_3.upper()
print(
    f"I: The nucleotide sequence {sequence_to_be_added_5.upper()} has been added to the 5' end all probe sequences."
)
print(
    f"I: The nucleotide sequence {sequence_to_be_added_3.upper()} has been added to the 3' end all probe sequences."
)

I: The nucleotide sequence  has been added to the 5' end all probe sequences.
I: The nucleotide sequence CCTGT has been added to the 3' end all probe sequences.

### egalize length
dfprobes['seq_length'] = dfprobes['seq'].apply(len)

if max(dfprobes['seq_length']) != min(dfprobes['seq_length']):
    print('I: Probes length is not uniform, detected range: %i ..%i' %
          (min(dfprobes['seq_length']), max(dfprobes['seq_length'])))
    max_length = max(dfprobes['seq_length'])
    dfprobes['padded_sequence'] = dfprobes['seq'].apply(
        lambda seq: seq + ((max_length - len(seq)) * '-'))
    print(
        "I: Probe sequences have been padded at the 5' to the uniform length of %i nucleotides"
        % max_length)
else:
    print('I: Probe sequences have the uniform length of %i nucleotides' %
          (dfprobes['seq_length'].median()))
    dfprobes['padded_sequence'] = dfprobes['seq']

print('I: Total datasets contains %i sequences.' % len(dfprobes))

# visualize composition of each position
df_nucleotides = mf.split_sequence_in_nucleotides(dfprobes['padded_sequence'])
dfcount = pd.DataFrame(index=['A', 'C', 'G', 'T', 'U', '-'])
for column in df_nucleotides:
    dfcount[column] = df_nucleotides[column].value_counts()
dfcount = dfcount.fillna(0)  #zeros for NaN
dfcount.transpose().plot(figsize=(15, 5), kind='bar')
print('I: Visualisation of the base composition per position')
print(
    'I: If positions are invariant they can be removed before sequence analysis.'
)

I: Probes length is not uniform, detected range: 36 ..40
I: Probe sequences have been padded at the 5' to the uniform length of 40 nucleotides
I: Total datasets contains 40330 sequences.
I: Visualisation of the base composition per position
I: If positions are invariant they can be removed before sequence analysis.

# You may remove invariant continuos positions by adjusting the slicing.
# It is recommended to leave a few invariant positions to allow for binding events
# between the variable and constant part of the probes.

dfprobes['padded_sequence'] = dfprobes['padded_sequence'].apply(lambda s: s[:38])  ### <==== do the slicing here

# visualize composition of each position
print('I: Visualisation of the base composition per position after slicing.')
df_nucleotides = mf.split_sequence_in_nucleotides(dfprobes['padded_sequence'])
dfcount = pd.DataFrame(index=['A', 'C', 'G', 'T', 'U', '-'])
for column in df_nucleotides:
    dfcount[column] = df_nucleotides[column].value_counts()
dfcount = dfcount.fillna(0)  #zeros for NaN
dfcount.transpose().plot(figsize=(15, 5), kind='bar')
plt.show()

# preparation for later classification
mean = dfprobes['signal binding'].mean()
std = dfprobes['signal binding'].std()
THRESHOLD = mean + 4 * std  #4*std used according to Weirauch et al., 2013
dfprobes['positive probe'] = dfprobes['signal binding'].apply(
    lambda s: True if s > THRESHOLD else False)

print(
    'I: The whole dataset has been used to set the threshold for a positive probe.'
)
print('I: The threshold is %f' % THRESHOLD)
print(
    f"I: {len(dfprobes[dfprobes['positive probe']])} probes of {len(dfprobes)} are above threshold."
)

if len(dfprobes[dfprobes['positive probe']]) == 0:
    print(
        'E: No probe above THRESHOLD. Classification is not possible. Please adjust the THRESHOLD.'
    )

I: Visualisation of the base composition per position after slicing.

I: The whole dataset has been used to set the threshold for a positive probe.
I: The threshold is 27352.791992
I: 567 probes of 40330 are above threshold.

#### Shuffle and prepare dataset for training and testing

# shuffle and split
dfprobes = shuffle(dfprobes)
dftrain, dftest = train_test_split(dfprobes, test_size=0.2)

print(
    'I: The whole dataset has been split in training (80%) and test (20%) datasets.'
)

# display histogramms of test and training set
dftrain['signal binding'].plot(kind='hist', bins=25).axvline(x=THRESHOLD, color='r', linestyle='-.', lw=0.5, label='threshold classification')
dftest['signal binding'].plot(kind='hist', bins=25)
plt.show()

# generate a subset with maximal 1000 probes

downsampled_size = 1000  # You may change downsampled size here.

percentile = 0.5 * downsampled_size / len(
    dftrain
) * 100  #percentile required for lowest and highest to achieve down-sampled size
if percentile < 4:
    percentile = 4  #do not use only the extreme values
elif percentile > 10:
    percentile = 10  #avoid taking value from the mid-range

if len(dftrain) * percentile * 2 / 100 < downsampled_size / 4:
    print('W: The subset only contains %i probes - a rather low number.' %
          dftrain * percentile * 2 / 100)

print(
    'I: A downsampled dataset containing the lowest and highest %.1f %% of the dataset is generated.'
    % percentile)
dfsubset_high = dftrain[dftrain['signal binding'] >= dftrain['signal binding'].quantile(1 - percentile / 100)]  # highest part
dfsubset_low = dftrain[dftrain['signal binding'] <= dftrain['signal binding'].quantile(percentile / 100)]  # lowest part
print('I: Median values of lowest and highest %.1f %%:  %r  %r' %
      (percentile, dfsubset_low['signal binding'].quantile(0.5),
       dfsubset_high['signal binding'].quantile(0.5)))

if len(dfsubset_high) + len(dfsubset_low) > downsampled_size:
    print('I: The dataset is further downsampled to %i sequences.' %
          downsampled_size)
    dfsubset_high = dfsubset_high.sample(downsampled_size - int(downsampled_size / 2))
    dfsubset_low = dfsubset_low.sample(int(downsampled_size / 2))
    dfsubset = pd.concat([dfsubset_high, dfsubset_low])
else:
    dfsubset = pd.concat([dfsubset_high, dfsubset_low])

dfsubset = shuffle(dfsubset)   
    
# display main properties of downsampled data set
print('I: Histogramm of the downsampled dataset along the with classification threshold.')
dfsubset['signal binding'].plot(kind='hist', bins=25).axvline(x=THRESHOLD, color='r', linestyle='-.', lw=0.5, label='threshold classification')
plt.show()

# establish numpy arrays of the sequenc and binding data in the dataframes

# complete data
X=mf.hotencode_sequence(dfprobes['padded_sequence'], nuc_type=NUC_TYPE)
y=np.array(dfprobes['signal binding'])

# training set
X_train=mf.hotencode_sequence(dftrain['padded_sequence'], nuc_type=NUC_TYPE)
y_train=np.array(dftrain['signal binding'])

# subset of training set
X_subset=mf.hotencode_sequence(dfsubset['padded_sequence'], nuc_type=NUC_TYPE)
y_subset=np.array(dfsubset['signal binding'])

# test set
X_test=mf.hotencode_sequence(dftest['padded_sequence'], nuc_type=NUC_TYPE)
y_test=np.array(dftest['signal binding'])

I: The whole dataset has been split in training (80%) and test (20%) datasets.

I: A downsampled dataset containing the lowest and highest 4.0 % of the dataset is generated.
I: Median values of lowest and highest 4.0 %:  643.771240234375  21367.48046875
I: The dataset is further downsampled to 1000 sequences.
I: Histogramm of the downsampled dataset along the with classification threshold.

### perform a quick & dirty round for a short motif by fitting on subset to check data integrity

#fit regression quick_model
quick_model=mf.findmotif(motif_length=3, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS, ftol=0.01)

start = time()
quick_model.fit(X_subset,y_subset)
print("I: Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
quick_model.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('quick', quick_model)
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Optimization took 0.06 hours.
I: energy matrix and logos:

        A      C      G      T
0 -15451  17539  11356 -13444
1  -3272   1701   -832   2403
2   1443  -3646   3145   -942

I: summed absolute energies of each position:
0    57791
1     8210
2     9178
dtype: int64

I: averaged summed energy over all positions: 25060
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: -4827 +/- 16012
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.06700 .. 0.67815 (ratio: 10.1)
I: number of probes: 1000
I: Pearson Correlation  r: 0.5278
I: mean absolute error: 9901.6968

WARNING:matplotlib.font_manager:findfont: Font family ['Arial'] not found. Falling back to DejaVu Sans.

I: Classification performance AUROC: 0.7207

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo
0	quick	Klf9	1000	3	0.527776	0.720653	-11473.366709	False	10.121019	0.678154	0.067004	-15451,..	suppressed

#### Perfrom GridCV Search for exploration of the motif length goal: identify the minimum motif length which gives a good r-value

# optional: allow for global optimization to verify whether the local optimization is good enough
# not recommended include fitG0=True. This option should only be considered when the local optimization is started with an approximate motif and the start parameter is set
# not recommended set time_dissociation. The effect of dissociation should be only considered when the local optimization is started with an approximate motif.


# prepare grid search over motif_length
model_grid=mf.findmotif(protein_conc=PROT_CONC, both_strands=BOTH_STRANDS)
param_grid = {"motif_length": [3,4,5,6,7,8]}     # choose sensible range for length of motif

# define custom refit function
def custom_refit(cv_results):
    """returns index of max r2/sqrt(motif_length)"""
    df_grid=pd.DataFrame(cv_results)
    index=(df_grid['mean_test_score']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))).idxmax()
    return index

# run grid search and refit according to custom refit
grid_search = GridSearchCV(model_grid, param_grid=param_grid, verbose=2, cv=5, refit=custom_refit, n_jobs=-1)

start = time()
grid_search.fit(X_subset, y_subset)

print("I: GridSearchCV took %.2f hours for %d candidate parameter settings."
    % ((time() - start)/3600, len(grid_search.cv_results_["params"])))
print('I: number of samples: %i' %len(X_subset))

df_grid=pd.DataFrame(grid_search.cv_results_)
print('I: Plot of r2 vs motif length and vs root(motif length)')
df_grid.rename(columns={'mean_test_score':'r2'}, inplace=True)
df_grid.plot(kind='scatter', x='param_motif_length', y='r2', yerr='std_test_score', figsize=(5,3)).set_xticks(param_grid["motif_length"])
df_grid['r2/sqrt(length)']=df_grid['r2']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))
df_grid['std/sqrt(length)']=df_grid['std_test_score']/(df_grid['param_motif_length'].apply(float).apply(np.sqrt))
df_grid.plot(kind='scatter', x='param_motif_length', y='r2/sqrt(length)',yerr='std/sqrt(length)', figsize=(5,3)).set_xticks(param_grid["motif_length"])
plt.show()

best_index=df_grid['r2/sqrt(length)'].idxmax()
CORE_MOTIF_LENGTH=df_grid.loc[best_index, 'param_motif_length']
print(f'I: The maximum ({CORE_MOTIF_LENGTH}) is suggested as CORE_MOTIF_LENGTH')

print('I: motif obtained with the best estimator from gridCV search')
# print & display results from best estimator
model_grid=grid_search.best_estimator_
model_grid.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('best grid', model_grid)
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

Fitting 5 folds for each of 6 candidates, totalling 30 fits
I: GridSearchCV took 1.41 hours for 6 candidate parameter settings.
I: number of samples: 1000
I: Plot of r2 vs motif length and vs root(motif length)

I: The maximum (8) is suggested as CORE_MOTIF_LENGTH
I: motif obtained with the best estimator from gridCV search
I: energy matrix and logos:

        A      C      G     T
0  -8695   3711   5404  -420
1  -6270   5634  -2266  2902
2   5788 -11474   6184  -498
3   1503   3957  -6287   826
4  11595   9556 -13882 -7270
5   -978   1574    337  -933
6   -107   -345    658  -204
7   -192   1132     22  -961

I: summed absolute energies of each position:
0    18232
1    17074
2    23946
3    12574
4    42304
5     3824
6     1316
7     2309
dtype: int64

I: averaged summed energy over all positions: 15197
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: 1698 +/- 15663
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00019 .. 1.78969 (ratio: 9486.8)
I: number of probes: 1000
I: Pearson Correlation  r: 0.7919
I: mean absolute error: 6779.7427

I: Classification performance AUROC: 0.8850

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo
0	quick	Klf9	1000	3	0.527776	0.720653	-11473.366709	False	10.121019	0.678154	0.067004	-15451,..	suppressed
1	best grid	Klf9	1000	8	0.791868	0.885009	3085.476013	False	9486.823691	1.789690	0.000189	-8695,..	suppressed

### run a number of identical optimizations with motif length found during grid search
### goal: find best motif through repetition, judge stabiltiy of optimization

#CORE_MOTIF_LENGTH=5  # adjust core motif length if needed, motif length can be changed later

# prepare for ipyparallel
number_of_optimizations = 20
model_list = [mf.findmotif(motif_length=CORE_MOTIF_LENGTH, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS)] * number_of_optimizations
X_list = [X_subset] * number_of_optimizations
y_list = [y_subset] * number_of_optimizations


def single_job(model, X, y):
    model.fit(X, y)
    return {'model':model}

# run the optimizations on ipp.cluster
start = time()
with ipp.Cluster(log_level=40) as rc:
    rc[:].use_pickle()
    view = rc.load_balanced_view()
    asyncresult = view.map_async(single_job, model_list, X_list, y_list)
    asyncresult.wait_interactive()
    result = asyncresult.get()
print("I: Optimization took %.2f hours." % ((time() - start) / 3600))


  
# assemble results and analyze
df_repetitions=pd.DataFrame(result)
df_repetitions['r (subset)']=df_repetitions['model'].apply(lambda e: e.rvalue)
df_repetitions['r (train)']=df_repetitions['model'].apply(lambda e: mf.linregress(e.predict(X_train),y_train).rvalue)
df_repetitions['r (test)']=df_repetitions['model'].apply(lambda e: mf.linregress(e.predict(X_test),y_test).rvalue)
df_repetitions['G0']=df_repetitions['model'].apply(lambda e: e.finalG0_)
df_repetitions['max binding']=df_repetitions['model'].apply(lambda e: e.max_binding_fit)
df_repetitions['min binding']=df_repetitions['model'].apply(lambda e: e.min_binding_fit)
df_repetitions['ratio'] = df_repetitions['model'].apply(lambda e: e.ratio)
df_repetitions['energies']=df_repetitions['model'].apply(lambda e: e.energies_)
#df_repetitions['information']=df_repetitions['model'].apply(lambda e: mf.energies2information(e.energies_))


# display results of the ensemble of optimizations
print('I: Results of the repeated motif finding, sorted according to the regression coefficient with the train dataset')
df_repetitions.sort_values('r (train)', ascending=False, inplace=True)
mf.display_df(df_repetitions, nuc_type=NUC_TYPE)

  0%|          | 0/16 [00:00<?, ?engine/s]

single_job:   0%|          | 0/20 [00:00<?, ?tasks/s]

I: Optimization took 0.97 hours.
I: Results of the repeated motif finding, sorted according to the regression coefficient with the train dataset

	model	r (subset)	r (train)	r (test)	G0	max binding	min binding	ratio	energies	logo
16	suppressed	0.886036	0.753992	0.765712	3085.476013	0.539078	0.000099	5429.581457	-803,..
0	suppressed	0.870561	0.753016	0.760949	3085.476013	0.853888	0.000134	6364.118907	-968,..
2	suppressed	0.872734	0.743548	0.764665	3085.476013	1.000380	0.000123	8121.875642	709,..
12	suppressed	0.872361	0.742599	0.763691	3085.476013	0.792200	0.000180	4396.883533	536,..
15	suppressed	0.872171	0.742351	0.763991	3085.476013	0.945555	0.000034	27544.090179	737,..
1	suppressed	0.872266	0.742338	0.764172	3085.476013	0.921576	0.000057	16202.467420	604,..
9	suppressed	0.871816	0.741203	0.762685	3085.476013	0.934662	0.000080	11635.921264	556,..
18	suppressed	0.872099	0.740746	0.763117	3085.476013	0.933755	0.000097	9578.458210	778,..
17	suppressed	0.871290	0.740542	0.760765	3085.476013	0.770541	0.000326	2365.986781	621,..
6	suppressed	0.867937	0.738625	0.760049	3085.476013	0.863910	0.000102	8434.655988	-2441,..
5	suppressed	0.872236	0.738578	0.759994	3085.476013	0.463461	0.000071	6548.460383	535,..
10	suppressed	0.858290	0.733919	0.751247	3085.476013	1.044942	0.000098	10660.187465	8793,..
11	suppressed	0.842570	0.728193	0.751873	3085.476013	0.497516	0.000025	19914.180170	-9618,..
19	suppressed	0.842480	0.722510	0.745732	3085.476013	0.421005	0.000022	18895.447036	-7386,..
14	suppressed	0.792270	0.542519	0.552038	3085.476013	1.843514	0.000444	4152.279496	-8401,..
4	suppressed	0.794535	0.538746	0.547611	3085.476013	1.929420	0.000396	4875.330142	-8813,..
13	suppressed	0.780005	0.493604	0.508688	3085.476013	1.382613	0.000869	1591.608668	-1522,..
8	suppressed	0.780314	0.492755	0.508738	3085.476013	1.443436	0.000388	3720.572172	567,..
3	suppressed	0.766615	0.464542	0.464071	3085.476013	5.949067	0.000396	15039.269709	-798,..
7	suppressed	0.642354	0.317320	0.325259	3085.476013	1.829086	0.000448	4084.993659	-4114,..

### compare energy matrices of ensemble using PCA
print('I: Histogram of the regression coefficients r obtained by repeated optimizaion with the subset.')
df_repetitions['r (subset)'].plot(kind='hist')
plt.show()

pca = PCA(n_components=2)
pca_2c=pca.fit_transform(df_repetitions['energies'].tolist())    
df_repetitions[['PCA1', 'PCA2']]=pca_2c

if sum(pca.explained_variance_ratio_)<0.5:
      print('W: 2-dimensional PCA explained only %i %% of variance' %(sum(pca.explained_variance_ratio_)*100))
else:
    print('I: 2-dimensional PCA explained %i %% of variance.' %(sum(pca.explained_variance_ratio_)*100))
print('I: Visualization of the PCA with the regression quality vs. subset and training dataset by color.')        
df_repetitions.plot(x='PCA1', y='PCA2', kind='scatter', c='r (subset)',cmap=cm.coolwarm, edgecolors='black', linewidths=0.3)
df_repetitions.plot(x='PCA1', y='PCA2', kind='scatter', c='r (train)',cmap=cm.coolwarm, edgecolors='black', linewidths=0.3)

I: Histogram of the regression coefficients r obtained by repeated optimizaion with the subset.

I: 2-dimensional PCA explained 58 % of variance.
I: Visualization of the PCA with the regression quality vs. subset and training dataset by color.

/home/GLipps/.local/lib/python3.8/site-packages/sklearn/utils/deprecation.py:101: FutureWarning: Attribute `n_features_` was deprecated in version 1.2 and will be removed in 1.4. Use `n_features_in_` instead.
  warnings.warn(msg, category=FutureWarning)

<matplotlib.axes._subplots.AxesSubplot at 0x7fb307785400>

# visualisation of the motif with the highest r with the train dataset
print('I: Best motif according to r (train) from the repeated optimizations.')
print('I: PCA components: %i, %i' %(df_repetitions.iloc[0]['PCA1'], df_repetitions.iloc[0]['PCA2']))
model_best_repetition=df_repetitions.iloc[0]['model']
model_best_repetition.analyse_motif(X_subset,y_subset, THRESHOLD, nuc_type=NUC_TYPE) 
# store results and display stages
STAGES.append('best repetition', model_best_repetition, new_entries={'r (test)': mf.linregress(model_best_repetition.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Best motif according to r (train) from the repeated optimizations.
I: PCA components: -9122, 26091
I: energy matrix and logos:

        A      C     G     T
0   -803   -104   191   716
1    353    310  1798 -2462
2 -12641  14598  6282 -8238
3  -4162   2514 -2482  4130
4   1176  -8364  9691 -2503
5   -785   5587 -4258  -543
6   8667   4426 -8137 -4956
7   -531    732   419  -620

I: summed absolute energies of each position:
0     1816
1     4924
2    41761
3    13291
4    21735
5    11174
6    26188
7     2303
dtype: int64

I: averaged summed energy over all positions: 15399
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: 2425 +/- 15600
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00010 .. 0.53908 (ratio: 5429.6)
I: number of probes: 1000
I: Pearson Correlation  r: 0.8860
I: mean absolute error: 4897.7168

I: Classification performance AUROC: 0.9372

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Klf9	1000	3	0.527776	0.720653	-11473.366709	False	10.121019	0.678154	0.067004	-15451,..	suppressed		NaN
1	best grid	Klf9	1000	8	0.791868	0.885009	3085.476013	False	9486.823691	1.789690	0.000189	-8695,..	suppressed		NaN
2	best repetition	Klf9	1000	8	0.886036	0.937161	3085.476013	False	5429.581457	0.539078	0.000099	-803,..	suppressed		0.765712

### motif finding on complete training dataset starting with best motif from repetitions

#fit & predict optimization starting with previous energy matrix
model_train=mf.findmotif(motif_length=CORE_MOTIF_LENGTH, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=model_best_repetition.energies_)
start = time()
model_train.fit(X_train,y_train)
print("I: Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
model_train.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('train dataset', model_train, new_entries={'r (test)': mf.linregress(model_train.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)

I: Optimization took 12.61 hours.
I: energy matrix and logos:

        A     C     G     T
0  -1250   234    45   969
1   1236   632  2870 -4738
2 -11633  9581  6423 -4371
3  -6211  2924 -3311  6598
4   1731 -8714  5776  1207
5    871  3729 -5446   846
6   5120  1810 -6185  -745
7   -435  1269   499 -1333

I: summed absolute energies of each position:
0     2501
1     9477
2    32010
3    19045
4    17429
5    10893
6    13861
7     3538
dtype: int64

I: averaged summed energy over all positions: 13594
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: 1859 +/- 12872
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00004 .. 1.58737 (ratio: 43208.5)
I: number of probes: 32264
I: Pearson Correlation  r: 0.8035
I: mean absolute error: 2043.4959

I: Classification performance AUROC: 0.9909

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Klf9	1000	3	0.527776	0.720653	-11473.366709	False	10.121019	0.678154	0.067004	-15451,..	suppressed		NaN
1	best grid	Klf9	1000	8	0.791868	0.885009	3085.476013	False	9486.823691	1.789690	0.000189	-8695,..	suppressed		NaN
2	best repetition	Klf9	1000	8	0.886036	0.937161	3085.476013	False	5429.581457	0.539078	0.000099	-803,..	suppressed		0.765712
3	train dataset	Klf9	32264	8	0.803464	0.990876	3085.476013	False	43208.465451	1.587371	0.000037	-1250,..	suppressed		0.818591

### Based on the motif of CORE_MOTIF_LENGTH analyze the neigbouring positions 
### whether their inclusion can improve the quality of the motif
df_positions=model_train.investigate_extension_parallel(X_train,y_train, end5=3, end3=3, nuc_type=NUC_TYPE)

list_positions=df_positions.index[df_positions['+2%']].tolist()+[0] # list of positions with an increase of2% and default position 0
ext5=-min(list_positions)
ext3=max(list_positions)
print("I: It is suggested to extend the core motif at the 5' end by %i and at the 3' end by %i positions." %(ext5, ext3))

### Analyze model whether the estimated G0 is correct
df_G0=model_train.investigate_G0(X_train,y_train)

  0%|          | 0/6 [00:00<?, ?engine/s]

job5:   0%|          | 0/3 [00:00<?, ?tasks/s]

job3:   0%|          | 0/3 [00:00<?, ?tasks/s]

I: Optimization took 0.35 hours.

I: It is suggested to extend the core motif at the 5' end by 2 and at the 3' end by 0 positions.
I: Current G0 = 3085 J/mol (see red broken line in figure below) with r = 0.803.
I: Maximal r is 0.803 at G0=3085 J/mol (see green broken line below).
I: Maximal occupancy of 2 is reached at G0=1085 J/mol (see blue broken line below).
I: Maximal occupancy of 0.2 is reached at G0=11085 J/mol (see blue broken line below).

I: G0 is in a range leading to maximal probe occupancy between 0.2 and 2. Good.
I: Current G0 is close to the G0 leading to maximal r. Good.

### fit & predict optimization starting with extended energy matrix if extension appears to improve prediction

if ext5+ext3!=0: #extension suggestion from previous analysis of the bordering positions
    expanded_energies=model_train.energies_
    # append energies of single-optimized bordering positions to energies of central part
    if ext5!=0:
        energies_5=np.concatenate(df_positions['energies'][(df_positions.index<0) & (df_positions.index>=-ext5)].to_numpy())
        expanded_energies=np.concatenate((energies_5, expanded_energies))
    if ext3!=0:
        energies_3=np.concatenate(df_positions['energies'][(df_positions.index<=ext3) & (df_positions.index>0)].to_numpy().flatten())
        expanded_energies=np.concatenate((expanded_energies,  energies_3))

    mf.energies2logo(expanded_energies, nuc_type=NUC_TYPE)
    print('I: Optimization started with extended motif.')
    expanded_motif_length=len(expanded_energies)//4
    
    
    model_extended=mf.findmotif(motif_length=expanded_motif_length, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=expanded_energies)

    start = time()
    model_extended.fit(X_train,y_train)
    print("Optimization took %.2f hours." % ((time() - start)/3600))

    # print & display main results
    model_extended.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

    # store results and display stages
    STAGES.append('train, extended', model_extended, new_entries={'r (test)': mf.linregress(model_extended.predict(X_test),y_test).rvalue})
    mf.display_df(STAGES.df, nuc_type=NUC_TYPE)
else:
    model_extended=model_train
    print('I: Motif is not extended based on previous analysis.')

I: Optimization started with extended motif.
Optimization took 10.91 hours.
I: energy matrix and logos:

        A      C     G     T
0  -1189   1185  -225   229
1   -303    268   239  -204
2  -1196    255    77   862
3   1160    705  2827 -4692
4 -14656  15737  6434 -7515
5  -6670   2697 -3794  7767
6   1199  -9639  8109   330
7    699   3777 -5481  1004
8   4391   2379 -6098  -672
9   -469   1263   576 -1370

I: summed absolute energies of each position:
0     2830
1     1015
2     2392
3     9385
4    44345
5    20929
6    19278
7    10962
8    13542
9     3679
dtype: int64

I: averaged summed energy over all positions: 12836
I: Mean and Standard Deviation for the Free Energy G to all subsequences of all probes: 3915 +/- 16300
I: Plot of the Occupancy of a subsite as the function of the Free Energy G 
   overlaid with the distribution of the Free Energy of all subsites.
I: There shall be only a small overlap of both curves. i.e. only the most negative Free Energies
    lead to a measurable occupancy.

I: Calculated occupancy over all subsite of a single probe:
   binding:  0.00001 .. 1.61221 (ratio: 147258.8)
I: number of probes: 32264
I: Pearson Correlation  r: 0.8352
I: mean absolute error: 1943.9151

I: Classification performance AUROC: 0.9931

	stage	protein	# probes	motif length	r	AUROC	G0	G0 fitted	ratio	max binding	min binding	energies	model	logo	r (test)
0	quick	Klf9	1000	3	0.527776	0.720653	-11473.366709	False	10.121019	0.678154	0.067004	-15451,..	suppressed		NaN
1	best grid	Klf9	1000	8	0.791868	0.885009	3085.476013	False	9486.823691	1.789690	0.000189	-8695,..	suppressed		NaN
2	best repetition	Klf9	1000	8	0.886036	0.937161	3085.476013	False	5429.581457	0.539078	0.000099	-803,..	suppressed		0.765712
3	train dataset	Klf9	32264	8	0.803464	0.990876	3085.476013	False	43208.465451	1.587371	0.000037	-1250,..	suppressed		0.818591
4	train, extended	Klf9	32264	10	0.835230	0.993097	7518.696033	False	147258.814946	1.612210	0.000011	-1189,..	suppressed		0.852736

### fit & predict optimization starting with extended energy matrix plus one bordering position on each side if current bordering position exceed the information of 0.25

I_5=mf.energies2information(model_extended.energies_[0:4])>=0.25 #sufficient information content of 5' end position
I_3=mf.energies2information(model_extended.energies_[-4:])>=0.25 #sufficient information content of 3' end position

if I_5 or I_3:
    print('I: At least one of the bordering positions has an information content of at least 0.25. Extending.')
    expanded_energies_with_border=mf.modify_energies(model_extended.energies_, end5=I_5, end3=I_3)  
    mf.energies2logo(expanded_energies_with_border, nuc_type=NUC_TYPE)
    motif_length_with_border=len(expanded_energies_with_border)//4

    model_with_border=mf.findmotif(motif_length=motif_length_with_border, protein_conc=PROT_CONC, both_strands=BOTH_STRANDS,
                   start=expanded_energies_with_border)


    start = time()
    model_with_border.fit(X_train,y_train)
    print("Optimization took %.2f hours." % ((time() - start)/3600))

    # print & display main results
    model_with_border.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

    # store results and display stages
    STAGES.append('train, expanded, border', model_with_border, new_entries={'r (test)': mf.linregress(model_with_border.predict(X_test),y_test).rvalue})
    mf.display_df(STAGES.df, nuc_type=NUC_TYPE)
else:
    print('I: Both bordering positions of the found motif have an information content below 0.25. No futher optimization required.')

I: Both bordering positions of the found motif have an information content below 0.25. No futher optimization required.

### Analyze model whether the estimated G0 is correct
df_G0=model_extended.investigate_G0(X_train,y_train)

I: Current G0 = 7519 J/mol (see red broken line in figure below) with r = 0.835.
I: Maximal r is 0.835 at G0=7519 J/mol (see green broken line below).
I: Maximal occupancy of 2 is reached at G0=5519 J/mol (see blue broken line below).
I: Maximal occupancy of 0.2 is reached at G0=15519 J/mol (see blue broken line below).

I: G0 is in a range leading to maximal probe occupancy between 0.2 and 2. Good.
I: Current G0 is close to the G0 leading to maximal r. Good.

STAGES.df.to_json('%s_%s-%s-%s_%s-%s.json' %(PROTEIN_NAME, datetime.now().year, datetime.now().month,datetime.now().day , datetime.now().hour, datetime.now().minute))
STAGES.df.to_pickle('%s_%s-%s-%s_%s-%s.pkl' %(PROTEIN_NAME, datetime.now().year, datetime.now().month,datetime.now().day , datetime.now().hour, datetime.now().minute))

mf.energies2logo(mf.reverse_complement(STAGES.df.at[3,'energies']), nuc_type=NUC_TYPE)

	A	C	G	T
0	-1333.569624	499.448110	1269.897878	-435.776364
1	-745.014775	-6185.798662	1810.582895	5120.230543
2	846.068567	-5446.563692	3729.124107	871.371018
3	1207.567928	5776.085161	-8714.665334	1731.012245
4	6598.554401	-3311.284649	2924.250189	-6211.519941
5	-4371.331301	6423.285490	9581.939541	-11633.893730
6	-4738.970386	2870.539792	632.293995	1236.136599
7	969.831012	45.818567	234.947275	-1250.596854

"""
expanded_energies=mf.modify_energies(model_train.energies_, end5=ext5, end3=ext3)  # <==== adjust end5 and end3 to enlarge core motif on 5' and 3' end
mf.energies2logo(expanded_energies, nuc_type=NUC_TYPE)
expanded_motif_length=len(expanded_energies)//4
"""

df_stages.drop(index='best grid fitG0=True', inplace=True)

import importlib

importlib.reload(mf)

start = time()
model_mae=model_with_border.refit_mae(X,y)
print("Optimization took %.2f hours." % ((time() - start)/3600))

# print & display main results
model_mae.analyse_motif(X_train,y_train, THRESHOLD, nuc_type=NUC_TYPE)

# store results and display stages
STAGES.append('train, expanded, border, mae', model_mae, new_entries={'r (test)': mf.linregress(model_mae.predict(X_test),y_test).rvalue})
mf.display_df(STAGES.df, nuc_type=NUC_TYPE)